pull down to refresh

0 sats \ 2 replies \ @optimism 22 Aug \ parent \ on: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing AI
I read that as: when you gamble twice, you have a greater chance to win once. lol
write
preview
100 sats \ 1 reply \ @carter OP 22 Aug
I think the big thing is this: Just random is the same no matter the delay, picking the fastest of 2 is much better but not that much worse than picking from 3. It seems similar to this strategy https://www.tiktok.com/t/ZP8BD7XQp/
reply
0 sats \ 0 replies \ @optimism 22 Aug
bro made me watch tiktok!
It's a good theory, but the reason why I say gamble is because of the randomization going on, even in MoE, where it's been reduced a lot. I'm not sure how this works in gpt-5 or claude-4 though, so maybe that's worth testing too.
reply